A study on word vector dimensions for sentence classifications using convolutional neural networks

被引:0
作者
Takuya S. [1 ]
Satoshi Y. [2 ]
机构
[1] Graduate School of Information and Computer Science, Chiba Institute of Technology, 2-17-1, Tsudanuma, Narashino, Chiba
[2] Dept. of Computer Science, Chiba Institute of Technology, 2-17-1, Tsudanuma, Narashino, Chiba
关键词
Convolutional neural networks; Distributed representation of words; Natural language processing; Sentence classification; Word2vec;
D O I
10.1541/ieejeiss.139.1066
中图分类号
学科分类号
摘要
Recently, convolutional neural networks (CNNs) have achieved remarkable results on sentence classification problems. In these approaches, each word in the sentences is transformed to real number vectors (called word vectors) and the sentences as input data to the CNN are represented by the sequences of the word vectors. A dataset for training and testing for the CNN includes the large number of words, therefore the word vectors are embedded so high-dimentional space. As a result of this, the input data space of the CNN becomes very high. When the input data have high dimension, much training data are required for enough training of the CNN. It is not always possible, however, to get enough number of data for training. If the enough data cannot prepare for learning, it is desirable to decrease the dimension of input data. This paper shows the results that the smaller dimensional word vectors are applied to sentence classifications by CNNs. The results have shown that some dimensionality reduction does not effect too much to the accuracy of the sentence classifications by CNNs. © 2019 The Institute of Electrical Engineers of Japan.
引用
收藏
页码:1066 / 1079
页数:13
相关论文
共 50 条
[41]   Sentiment Analysis in Social Networks Using Convolutional Neural Networks [J].
Elfaik, Hanane ;
Nfaoui, El Habib .
ADVANCED INTELLIGENT SYSTEMS FOR SUSTAINABLE DEVELOPMENT (AI2SD'2020), VOL 2, 2022, 1418 :263-276
[42]   Text Classification with Topic-based Word Embedding and Convolutional Neural Networks [J].
Xu, Haotian ;
Dong, Ming ;
Zhu, Dongxiao ;
Kotov, Alexander ;
Carcone, April Idalski ;
Naar-King, Sylvie .
PROCEEDINGS OF THE 7TH ACM INTERNATIONAL CONFERENCE ON BIOINFORMATICS, COMPUTATIONAL BIOLOGY, AND HEALTH INFORMATICS, 2016, :88-97
[43]   Handwritten Word Image Categorization with Convolutional Neural Networks and Spatial Pyramid Pooling [J].
Ignacio Toledo, J. ;
Sudholt, Sebastian ;
Fornes, Alicia ;
Cucurull, Jordi ;
Fink, Gernot A. ;
Llados, Josep .
STRUCTURAL, SYNTACTIC, AND STATISTICAL PATTERN RECOGNITION, S+SSPR 2016, 2016, 10029 :543-552
[44]   Word Sense Disambiguation Based on Semi-Supervised Convolutional Neural Networks [J].
Zhang C. ;
Tang L. ;
Gao X. .
Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University, 2022, 57 (01) :11-17and27
[45]   Sentiment Analysis of Product Reviews in Russian using Convolutional Neural Networks [J].
Smetanin, Sergey ;
Komarov, Mikhail .
2019 IEEE 21ST CONFERENCE ON BUSINESS INFORMATICS (CBI), VOL 1, 2019, :482-486
[46]   Pashto Language Handwritten Numeral Classification Using Convolutional Neural Networks [J].
Khan, Muhammad Ahmad ;
Ahmad, Faizan ;
Khan, Khalil ;
Khan, Maqbool .
FORTHCOMING NETWORKS AND SUSTAINABILITY IN THE AIOT ERA, VOL 2, FONES-AIOT 2024, 2024, 1036 :287-297
[47]   RETRACTED ARTICLE: Composite feature vector based cardiac arrhythmia classification using convolutional neural networks [J].
Gopisetty Ramesh ;
Donthi Satyanarayana ;
Maruvada Sailaja .
Journal of Ambient Intelligence and Humanized Computing, 2021, 12 :6465-6478
[48]   Deep compare: A study on using convolutional neural networks to compare image patches [J].
Zagoruyko, S. ;
Komodakis, N. .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2017, 164 :38-55
[49]   Flattened Data in Convolutional Neural Networks: Using Malware Detection as Case Study [J].
Yeh, Chih-Wei ;
Yeh, Wan-Ting ;
Hung, Shih-Hao ;
Lin, Chih-Ta .
2016 RESEARCH IN ADAPTIVE AND CONVERGENT SYSTEMS, 2016, :130-135
[50]   Three-way enhanced convolutional neural networks for sentence-level sentiment classification [J].
Zhang, Yuebing ;
Zhang, Zhifei ;
Miao, Duoqian ;
Wang, Jiaqi .
INFORMATION SCIENCES, 2019, 477 :55-64